hisanusman/Violent-activities-detection-and-scene-understanding
This project uses a vision transformer to detect violent activities in CCTV footages, along with a custom YOLOv8 model for weapon detection and pin-pointing of exact person. Scene understanding has been implemented through CLIP, the results of which are used in automatic AI report generation via LangChain (GPT & FLAN-T5).
21
/ 100
Experimental
No Package
No Dependents
Maintenance
10 / 25
Adoption
0 / 25
Maturity
11 / 25
Community
0 / 25
Stars
—
Forks
—
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Mar 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/hisanusman/Violent-activities-detection-and-scene-understanding"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.